mrkeyoor.comAsk

facefusion/facefusiontested 30 Sept 2026commit 7247081

facefusion review

FaceFusion's documented headless, batch and job commands justify a controlled evaluation for repeatable face-manipulation work.

  • Install 29 s
  • Build 6 s
97/238passed, run exited non-zero
  • 87 packages
AI Toolsevaluationupdated 25 Oct 2026
+70stars / 7d

FaceFusion is a face-manipulation application with interactive, headless, batch and queued-job commands. Its documented automation options make it worth evaluating for repeatable media work, but our September 30, 2026 sandbox run at commit 7247081 did not establish working media processing or production readiness.

Verdict

FaceFusion's documented headless, batch and job commands justify a controlled evaluation for repeatable face-manipulation work. Our September 30, 2026 run at commit 7247081 recorded successful harness install and build steps, followed by a failing test step and 58 pip-audit advisories with unknown scan coverage. It did not establish application readiness, output quality or a product defect causing the failures. Before adoption, follow the official installation path, process consented sample media on your intended hardware, investigate the test and audit results, and review the selected models' licenses.

We ran it

Lab card: what happened when we ran facefusion
Lab card from our sandbox run
Screenshot of facefusion (facefusion.io)
facefusion.io
Install✓ · 29s87 packages · 780 MB
Build✓ · 6s
Tests✗ · 46s97 passed · 13 failed · 4 skipped · 128 errors of 238 (pytest)
Known vulns58(pip-audit)
Repo247 files~23,048 lines of source · 2.1 MB · 1 CI workflows · tests dir

Answers from our run

Does facefusion build from source?

Dependencies installed in 29 seconds (87 packages), and the build succeeded in 6 seconds. We cloned commit 7247081 into a clean Debian container with 3 CPUs and no project-specific setup.

Do facefusion's tests pass?

No. The project's own test command finished in 46 seconds and reported 97 passed, 13 failed, 4 skipped, 128 collection errors (pytest).

Does facefusion have known vulnerabilities in its dependencies?

pip-audit flagged 58 known advisories in the dependency tree at the time of our run.

Who should not use facefusion?

Beginners expecting the source installation to require no terminal knowledge. The README explicitly warns that installation needs technical skills and points to Windows and macOS installers.

What are the alternatives to facefusion?

Deep-Live-Cam, Rope. FaceFusion's documented headless, batch and job commands justify a controlled evaluation for repeatable face-manipulation work.

Setup2/5The documented path requires Conda and an execution-backend choice. Successful harness steps do not verify completed application setup.
Docs3/5The supplied README, installation, license and disclaimer extracts cover a baseline evaluation path; broader documentation completeness is unverified.
Community1/5Insufficient supplied evidence to assess support responsiveness, contributor breadth or adoption. This is an evidence limitation, not a finding of poor community support.
Maturity2/5Release 3.9.1 is documented, but the September 30, 2026 run at 7247081 leaves test and audit findings unresolved and media workloads unverified.

Discussed on

  1. hnFaceFusion: Next generation face swapper and enhancer73 points

Who it’s for

Technical users evaluating face-manipulation workflows who can follow the documented environment and accelerator setup.
Teams that want headless, batch or queued-job commands and can validate them on their intended hardware and consented media.
Users prepared to check the terms of each selected model separately from the application's license.

Who it’s NOT for

Beginners expecting the source installation to require no terminal knowledge. The README explicitly warns that installation needs technical skills and points to Windows and macOS installers.
Teams seeking demonstrated output quality, throughput or accelerator compatibility from this review. Our recorded run did not measure those workloads.
Commercial users assuming the application license covers every model. The license list includes Non-Commercial, ResearchRAIL and Unknown entries.
Users expecting the recorded dependency audit to establish safety or complete coverage. Its package coverage and finding details are unavailable.

Setup reality

In our recorded run on September 30, 2026 at commit 7247081, the harness marked the install step successful after 29 seconds and the build step successful after 6 seconds. It recorded 87 dependencies and a 780 MB installation metric. The install tail only identifies a Python 3.12.12 environment; the commands and build output are absent. These results do not establish that FaceFusion's application installer completed, an installed binary worked, or models and media dependencies were ready.

The test step exited 1 after 46 seconds. Its retained pytest summary reports 97 passed, 13 failed, 4 skipped and 128 errors in 39.83 seconds. The parser records total=238, but exhaustive unique coverage has not been reconciled. Do not add these categories together to claim a verified total or describe all errors as collection errors.

Pip-audit recorded 58 advisories associated with 3 packages. The number of scanned packages, affected package names, advisory identifiers, severity and reachability are not supplied. The 87-dependency metric does not establish audit coverage.

The documented installation creates a Conda environment with Python 3.12 and pip 25.0, then selects an installation path for CPU or an accelerator. This documented path is separate from what the retained sandbox output proves.

Automation is the reason to evaluate it

FaceFusion documents separate commands for interactive use, headless execution, batches and queued jobs. That gives a technical evaluator a concrete question: can its command and job workflow reproduce the media processing their team needs?

The README lists headless-run, batch-run and commands to create, submit, run, retry and delete jobs. Those are documented capabilities, not workloads verified by our sandbox. We did not measure output quality, processing speed, webcam behavior or accelerator compatibility.

Follow the documented installation path

The README warns that source installation needs technical skills and is not recommended for beginners. It also points readers who are uncomfortable with a terminal to Windows and macOS installers. We did not evaluate those installers.

The installation guide initializes Conda and creates an environment with Python 3.12 and pip 25.0. It then covers platform preparation, accelerator setup, cloning the repository, installing the application and reactivating the environment. The supplied guide lists CPU, CUDA, CoreML, DirectML, MIGraphX and OpenVINO installation choices. It ends with python facefusion.py run --open-browser.

Treat those instructions as the next step for a trial. Our retained harness output does not show which installation command ran or establish that the documented application setup completed.

What our recorded run establishes

Our stored run began on September 30, 2026 at 12:30:19.677 UTC and used commit 72470819a0373be3388b3929c8f8f311f418fc3c, abbreviated 7247081. The release page associates 3.9.1 with that abbreviated commit. The recorded sandbox had 3 CPUs, 8 GB of memory and image ghcr.io/astral-sh/uv:python3.12-bookworm. The install tail identifies Python 3.12.12 at /work/home/venv.

The harness marked install successful in 29 seconds and build successful in 6 seconds. It recorded 87 dependencies and a 780 MB installation metric. The checkout metrics were 247 files, approximately 23,048 lines of source and 2.1 MB. The checkout detector found one CI workflow and no Dockerfile or Compose file. That observation does not establish whether separate container distribution options exist.

The install tail contains only the Python environment line, and the build tail is empty. Without the executed commands or fuller logs, neither successful step proves that FaceFusion launched, an installed binary worked, model downloads completed or a media job succeeded.

The test step exited 1 after 46 seconds of harness time. The retained pytest summary says 13 failed, 97 passed, 4 skipped and 128 errors in 39.83 seconds. The harness duration and pytest's reported duration describe different timing scopes.

The parser also records total=238. Its counts have not been reconciled against a complete log to establish exhaustive unique coverage. The 128 errors should therefore remain a reported error count, rather than become 128 additional failed tests or a verified count of collection errors.

The retained tail shows NoneType path errors in face-tracking, frame-storage, job, video and image tests; five inference-pool assertion failures; and a missing test module in the static-provider test. It does not establish their root causes. A failed test command in this environment does not prove the application is broken on a supported installation.

Pip-audit recorded 58 advisories associated with 3 packages. The record does not provide scanned-package coverage, package names, advisory identifiers, severity or evidence that vulnerable code was reachable. These are recorded audit findings requiring investigation, not proof of exploitation or 58 independently verified product vulnerabilities. Dependency count is not audit coverage.

Check model terms before choosing a preset

The license page says FaceFusion is distributed under OpenRAIL-AS and that supplied assets have individual licenses. Its model list includes MIT and Apache 2.0 entries alongside Non-Commercial, ResearchRAIL, S-Lab 1.0 and Unknown entries. Application licensing alone cannot settle whether your selected model combination is suitable for commercial work.

Record the exact models and revisions you intend to use, then review their terms for your intended use. The project's disclaimer also says the software is designed to abstain from processing nudity, graphic content and sensitive material. That is a maintainer statement about safeguards; our run did not test their effectiveness. Use consented material and establish permission to use the depicted people before evaluating output.

Two alternatives for different workflows

Deep-Live-Cam's README documents image/video processing and a webcam sequence: select a source face, choose a camera and start live mode. It is relevant when live swapping is the main task. Its setup and performance claims are not comparative measurements from this review.

Rope's README describes a GUI implementing InsightFace's inswapper_128 model, with settings for folders and models. It is relevant when that GUI and model workflow match your needs. The extract does not support calling Rope a leaner alternative.

How to read the scores

These are editorial evidence ratings, not benchmark results or failure probabilities. The scale is 1 for insufficient evidence to assess a category, 2 for substantial documented prerequisites or unresolved validation, 3 for a documented baseline, 4 for broad documentation or corroborated operational evidence, and 5 for broad evidence plus representative validation. An unknown category receives 1 because this review cannot substantiate a stronger assessment, not because the product has been shown to perform poorly.

Setup receives 2 because the documented path requires environment and accelerator decisions while our retained output leaves application setup unverified. Documentation receives 3 because the supplied README and installation, licensing and disclaimer pages cover a baseline evaluation path; we have not verified every linked page. Community receives 1 because the supplied extracts do not establish support responsiveness, contributor breadth or adoption. Maturity receives 2 because release 3.9.1 is documented, but the recorded test and audit results remain unresolved and representative media processing was not measured.

For a useful next trial, follow the official installation instructions on your intended hardware, record the commands and model choices, and process a small consented sample. Check the output and reproduce relevant tests before deciding whether the workflow meets your requirements.

Alternatives

ProjectWhat it isPick it when
Deep-Live-Cam gh↗A face-swap application whose README documents image/video and webcam modes.Evaluate it when selecting a source face and camera for live swapping is your main workflow. Its README documents that sequence; this review does not compare its speed, quality or setup reliability with FaceFusion.
RopeA GUI application implementing the InsightFace inswapper_128 model.Evaluate it when you want a GUI centered on inswapper_128 and its documented settings workflow. The supplied README supports that role, but does not establish that Rope is leaner or easier to install than FaceFusion.

What people are saying

  1. [velocity-scout] facefusion/facefusion

Sources

  1. FaceFusion README
  2. FaceFusion 3.9.1 release
  3. FaceFusion installation guide
  4. FaceFusion model license list
  5. FaceFusion disclaimer

More ai tools reviews